© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30053
    Prev
    Next
    INDEX
    Explanations

    HM The, HM Prison, HM_SENSE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wast
    -0.09
     deal
    -0.09
     dime
    -0.09
     Grat
    -0.09
    equal
    -0.09
    umber
    -0.08
     dealing
    -0.08
    wend
    -0.08
    uttle
    -0.08
     Evel
    -0.08
    POSITIVE LOGITS
    erus
    0.10
    eref
    0.09
    quan
    0.09
    ucken
    0.09
     modal
    0.09
    .hm
    0.08
     HM
    0.08
    Modal
    0.08
     coincidence
    0.08
    DAL
    0.08
    Activations Density 0.037%

    No Known Activations